> Discover all available pages from the documentation index: https://mastra.zisheng.pro/ko/llms.txt

# 마스트라의 목소리

Mastra의 음성 시스템은 음성 상호 작용을 위한 통합 인터페이스를 제공하여 애플리케이션에서 TTS(텍스트 음성 변환), STT(음성 변환) 및 실시간 STS(음성 변환) 기능을 활성화합니다.

## Agent에게 음성 추가

다음을 사용하여 음성 제공자를 Agent에게 전달합니다.`voice` 속성을 사용합니다. 구성한 Provider에 따라 동일한 속성에서 텍스트 음성 변환(TTS), 음성 텍스트 변환(STT), 실시간 음성 간 변환(STS)을 지원합니다.

```typescript
import { Agent } from '@mastra/core/agent'
import { OpenAIVoice } from '@mastra/voice-openai'

// Initialize OpenAI voice for TTS

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new OpenAIVoice(),
})
```

그런 다음 다음 음성 기능을 사용할 수 있습니다.

### 텍스트 음성 변환(TTS)

Mastra의 TTS 기능을 사용하여 Agent의 응답을 자연스러운 음성으로 변환하세요. OpenAI, ElevenLabs 등과 같은 여러 Provider 중에서 선택하세요.

자세한 구성 옵션과 고급 기능을 알아보려면 당사를 확인하세요.[Text-to-Speech guide](https://mastra.zisheng.pro/ko/guides/voice/text-to-speech).

**OpenAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { OpenAIVoice } from '@mastra/voice-openai'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new OpenAIVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
  responseFormat: 'wav', // Optional: specify a response format
})

playAudio(audioStream)
```

방문[OpenAI Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/openai) 에서 OpenAI 음성 Provider에 관한 자세한 정보를 확인하세요.

**Azure**:

```typescript
import { Agent } from '@mastra/core/agent'
import { AzureVoice } from '@mastra/voice-azure'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new AzureVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'en-US-JennyNeural', // Optional: specify a speaker
})

playAudio(audioStream)
```

방문[Azure Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/azure) 에서 Azure 음성 Provider에 관한 자세한 정보를 확인하세요.

**ElevenLabs**:

```typescript
import { Agent } from '@mastra/core/agent'
import { ElevenLabsVoice } from '@mastra/voice-elevenlabs'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new ElevenLabsVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
})

playAudio(audioStream)
```

방문[ElevenLabs Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/elevenlabs) 에서 ElevenLabs 음성 Provider에 관한 자세한 정보를 확인하세요.

**PlayAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { PlayAIVoice } from '@mastra/voice-playai'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new PlayAIVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
})

playAudio(audioStream)
```

방문[PlayAI Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/playai) 에서 PlayAI 음성 Provider에 관한 자세한 정보를 확인하세요.

**Google**:

```typescript
import { Agent } from '@mastra/core/agent'
import { GoogleVoice } from '@mastra/voice-google'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new GoogleVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'en-US-Studio-O', // Optional: specify a speaker
})

playAudio(audioStream)
```

방문[Google Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/google) 에서 Google 음성 Provider에 관한 자세한 정보를 확인하세요.

**Cloudflare**:

```typescript
import { Agent } from '@mastra/core/agent'
import { CloudflareVoice } from '@mastra/voice-cloudflare'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new CloudflareVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
})

playAudio(audioStream)
```

방문[Cloudflare Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/cloudflare) 에서 Cloudflare 음성 Provider에 관한 자세한 정보를 확인하세요.

**Deepgram**:

```typescript
import { Agent } from '@mastra/core/agent'
import { DeepgramVoice } from '@mastra/voice-deepgram'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new DeepgramVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'aura-english-us', // Optional: specify a speaker
})

playAudio(audioStream)
```

방문[Deepgram Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/deepgram) 에서 Deepgram 음성 Provider에 관한 자세한 정보를 확인하세요.

**Inworld**:

```typescript
import { Agent } from '@mastra/core/agent'
import { InworldVoice } from '@mastra/voice-inworld'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new InworldVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'Dennis', // Optional: specify a speaker
})

playAudio(audioStream)
```

방문[Inworld Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/inworld) 에서 Inworld 음성 Provider에 관한 자세한 정보를 확인하세요.

**Speechify**:

```typescript
import { Agent } from '@mastra/core/agent'
import { SpeechifyVoice } from '@mastra/voice-speechify'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new SpeechifyVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'matthew', // Optional: specify a speaker
})

playAudio(audioStream)
```

방문[Speechify Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/speechify) 에서 Speechify 음성 Provider에 관한 자세한 정보를 확인하세요.

**Sarvam**:

```typescript
import { Agent } from '@mastra/core/agent'
import { SarvamVoice } from '@mastra/voice-sarvam'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new SarvamVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'shubh', // Optional: specify a bulbul:v3 speaker
})

playAudio(audioStream)
```

방문[Sarvam Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/sarvam) 에서 Sarvam 음성 Provider에 관한 자세한 정보를 확인하세요.

**Murf**:

```typescript
import { Agent } from '@mastra/core/agent'
import { MurfVoice } from '@mastra/voice-murf'
import { playAudio } from '@mastra/node-audio'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new MurfVoice(),
})

const { text } = await voiceAgent.generate('What color is the sky?')

// Convert text to speech to an Audio Stream
const audioStream = await voiceAgent.voice.speak(text, {
  speaker: 'default', // Optional: specify a speaker
})

playAudio(audioStream)
```

방문[Murf Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/murf) 에서 Murf 음성 Provider에 관한 자세한 정보를 확인하세요.

### 음성을 텍스트로 변환(STT)

OpenAI, ElevenLabs 등과 같은 Provider를 사용하여 음성 콘텐츠를 텍스트로 변환하세요. 자세한 구성 옵션 등을 확인하려면 다음을 확인하세요.[Speech to Text](https://mastra.zisheng.pro/ko/guides/voice/speech-to-text).

다음에서 샘플 오디오 파일을 다운로드할 수 있습니다.[here](https://github.com/mastra-ai/realtime-voice-demo/raw/refs/heads/main/how_can_i_help_you.mp3).

[](https://github.com/mastra-ai/realtime-voice-demo/raw/refs/heads/main/how_can_i_help_you.mp3)

**OpenAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { OpenAIVoice } from '@mastra/voice-openai'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new OpenAIVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

방문[OpenAI Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/openai) 에서 OpenAI 음성 Provider에 관한 자세한 정보를 확인하세요.

**Azure**:

```typescript
import { createReadStream } from 'fs'
import { Agent } from '@mastra/core/agent'
import { AzureVoice } from '@mastra/voice-azure'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new AzureVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

방문[Azure Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/azure) 에서 Azure 음성 Provider에 관한 자세한 정보를 확인하세요.

**ElevenLabs**:

```typescript
import { Agent } from '@mastra/core/agent'
import { ElevenLabsVoice } from '@mastra/voice-elevenlabs'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new ElevenLabsVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

방문[ElevenLabs Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/elevenlabs) 에서 ElevenLabs 음성 Provider에 관한 자세한 정보를 확인하세요.

**Google**:

```typescript
import { Agent } from '@mastra/core/agent'
import { GoogleVoice } from '@mastra/voice-google'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new GoogleVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

방문[Google Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/google) 에서 Google 음성 Provider에 관한 자세한 정보를 확인하세요.

**Cloudflare**:

```typescript
import { Agent } from '@mastra/core/agent'
import { CloudflareVoice } from '@mastra/voice-cloudflare'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new CloudflareVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

방문[Cloudflare Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/cloudflare) 에서 Cloudflare 음성 Provider에 관한 자세한 정보를 확인하세요.

**Deepgram**:

```typescript
import { Agent } from '@mastra/core/agent'
import { DeepgramVoice } from '@mastra/voice-deepgram'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new DeepgramVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

방문[Deepgram Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/deepgram) 에서 Deepgram 음성 Provider에 관한 자세한 정보를 확인하세요.

**Inworld**:

```typescript
import { Agent } from '@mastra/core/agent'
import { InworldVoice } from '@mastra/voice-inworld'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new InworldVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

방문[Inworld Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/inworld) 에서 Inworld 음성 Provider에 관한 자세한 정보를 확인하세요.

**Sarvam**:

```typescript
import { Agent } from '@mastra/core/agent'
import { SarvamVoice } from '@mastra/voice-sarvam'
import { createReadStream } from 'fs'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new SarvamVoice(),
})

// Use an audio file from a URL
const audioStream = await createReadStream('./how_can_i_help_you.mp3')

// Convert audio to text
const transcript = await voiceAgent.voice.listen(audioStream)
console.log(`User said: ${transcript}`)

// Generate a response based on the transcript
const { text } = await voiceAgent.generate(transcript)
```

방문[Sarvam Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/sarvam) 에서 Sarvam 음성 Provider에 관한 자세한 정보를 확인하세요.

### 음성 대 음성(STS)

음성 대 음성 변환 기능으로 대화 환경을 조성하세요. 통합 API를 사용하면 사용자와 AI Agent 간의 실시간 음성 상호작용이 가능합니다. 자세한 구성 옵션과 고급 기능을 확인하려면 다음을 확인하세요.[Speech to Speech](https://mastra.zisheng.pro/ko/guides/voice/speech-to-speech).

**OpenAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { OpenAIRealtimeVoice } from '@mastra/voice-openai-realtime'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new OpenAIRealtimeVoice(),
})

// Listen for agent audio responses
voiceAgent.voice.on('speaker', ({ audio }) => {
  playAudio(audio)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

방문[OpenAI Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/openai-realtime) 에서 OpenAI 음성 Provider에 관한 자세한 정보를 확인하세요.

**Google**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { GeminiLiveVoice } from '@mastra/voice-google-gemini-live'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new GeminiLiveVoice({
    // Live API mode
    apiKey: process.env.GOOGLE_API_KEY,
    model: 'gemini-2.0-flash-exp',
    speaker: 'Puck',
    debug: true,
    // Vertex AI alternative:
    // vertexAI: true,
    // project: 'your-gcp-project',
    // location: 'us-central1',
    // serviceAccountKeyFile: '/path/to/service-account.json',
  }),
})

// Connect before using speak/send
await voiceAgent.voice.connect()

// Listen for agent audio responses
voiceAgent.voice.on('speaker', ({ audio }) => {
  playAudio(audio)
})

// Listen for text responses and transcriptions
voiceAgent.voice.on('writing', ({ text, role }) => {
  console.log(`${role}: ${text}`)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

방문[Google Gemini Live Reference](https://mastra.zisheng.pro/ko/reference/voice/google-gemini-live) 에서 Google Gemini Live 음성 Provider에 관한 자세한 정보를 확인하세요.

**AWS Nova Sonic**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { NovaSonicVoice } from '@mastra/voice-aws-nova-sonic'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new NovaSonicVoice({
    region: 'us-east-1',
    speaker: 'matthew',
    // Static credentials are optional. The default AWS credential
    // provider chain is used when none are passed.
  }),
})

// Connect before using speak/send
await voiceAgent.voice.connect()

// Listen for assistant audio (Int16Array PCM)
voiceAgent.voice.on('speaking', ({ audioData }) => {
  if (audioData) playAudio(audioData)
})

// Listen for transcribed text
voiceAgent.voice.on('writing', ({ text, role }) => {
  console.log(`${role}: ${text}`)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

방문[AWS Nova Sonic Reference](https://mastra.zisheng.pro/ko/reference/voice/aws-nova-sonic) 에서 AWS Nova Sonic 음성 Provider에 관한 자세한 정보를 확인하세요.

**Inworld Realtime**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { InworldRealtimeVoice } from '@mastra/voice-inworld'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'openai/gpt-5.6-sol',
  voice: new InworldRealtimeVoice({
    apiKey: process.env.INWORLD_API_KEY,
    model: 'inworld/models/gemma-4-26b-a4b-it',
    speaker: 'Sarah',
  }),
})

// Connect before using speak/send
await voiceAgent.voice.connect()

// Listen for agent audio (PCM stream)
voiceAgent.voice.on('speaker', stream => {
  playAudio(stream)
})

// Listen for text responses and transcriptions
voiceAgent.voice.on('writing', ({ text, role }) => {
  console.log(`${role}: ${text}`)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

방문[Inworld Realtime Reference](https://mastra.zisheng.pro/ko/reference/voice/inworld-realtime) 에서 Inworld Realtime 음성 Provider에 관한 자세한 정보를 확인하세요.

**xAI**:

```typescript
import { Agent } from '@mastra/core/agent'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'
import { XAIRealtimeVoice } from '@mastra/voice-xai-realtime'

const voiceAgent = new Agent({
  id: 'voice-agent',
  name: 'Voice Agent',
  instructions: 'You are a voice assistant that can help users with their tasks.',
  model: 'xai/grok-4.3',
  voice: new XAIRealtimeVoice({
    apiKey: process.env.XAI_API_KEY,
    model: 'grok-voice-think-fast-1.0',
    speaker: 'eve',
    turnDetection: { type: 'server_vad' },
  }),
})

// Connect before using speak/send
await voiceAgent.voice.connect()

// Listen for agent audio responses
voiceAgent.voice.on('speaker', audioStream => {
  playAudio(audioStream)
})

// Listen for text responses and transcriptions
voiceAgent.voice.on('writing', ({ text, role }) => {
  console.log(`${role}: ${text}`)
})

// Initiate the conversation
await voiceAgent.voice.speak('How can I help you today?')

// Send continuous audio from the microphone
const micStream = getMicrophoneStream()
await voiceAgent.voice.send(micStream)
```

방문[xAI Realtime Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/xai-realtime) 에서 xAI 음성 Provider에 관한 자세한 정보를 확인하세요.

### 실시간 음성

사용자가 브라우저나 전화를 통해 대화할 수 있는 실시간 통화를 실행하세요. Mastra는 음성 활동 감지, 의미론적 차례 감지 및 참여를 다루는 오디오 루프를 LiveKit에 전달하고 Agent는 자체 Model, Tool 및 Memory를 사용하여 각 응답을 생성합니다. 설정 및 구성 옵션을 확인하려면 다음을 확인하세요.[Realtime voice](https://mastra.zisheng.pro/ko/guides/voice/realtime-voice).

## 음성 구성

각 음성 Provider는 다양한 Model과 옵션으로 구성될 수 있습니다. 다음은 지원되는 모든 공급자에 대한 자세한 구성 옵션입니다.

**OpenAI**:

```typescript
// OpenAI Voice Configuration
const voice = new OpenAIVoice({
  speechModel: {
    name: 'gpt-3.5-turbo', // Example model name
    apiKey: process.env.OPENAI_API_KEY,
    language: 'en-US', // Language code
    voiceType: 'neural', // Type of voice model
  },
  listeningModel: {
    name: 'whisper-1', // Example model name
    apiKey: process.env.OPENAI_API_KEY,
    language: 'en-US', // Language code
    format: 'wav', // Audio format
  },
  speaker: 'alloy', // Example speaker name
})
```

방문[OpenAI Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/openai) 에서 OpenAI 음성 Provider에 관한 자세한 정보를 확인하세요.

**Azure**:

```typescript
// Azure Voice Configuration
const voice = new AzureVoice({
  speechModel: {
    name: 'en-US-JennyNeural', // Example model name
    apiKey: process.env.AZURE_SPEECH_KEY,
    region: process.env.AZURE_SPEECH_REGION,
    language: 'en-US', // Language code
    style: 'cheerful', // Voice style
    pitch: '+0Hz', // Pitch adjustment
    rate: '1.0', // Speech rate
  },
  listeningModel: {
    name: 'en-US', // Example model name
    apiKey: process.env.AZURE_SPEECH_KEY,
    region: process.env.AZURE_SPEECH_REGION,
    format: 'simple', // Output format
  },
})
```

방문[Azure Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/azure) 에서 Azure 음성 Provider에 관한 자세한 정보를 확인하세요.

**ElevenLabs**:

```typescript
// ElevenLabs Voice Configuration
const voice = new ElevenLabsVoice({
  speechModel: {
    voiceId: 'your-voice-id', // Example voice ID
    model: 'eleven_multilingual_v2', // Example model name
    apiKey: process.env.ELEVENLABS_API_KEY,
    language: 'en', // Language code
    emotion: 'neutral', // Emotion setting
  },
  // ElevenLabs may not have a separate listening model
})
```

방문[ElevenLabs Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/elevenlabs) 에서 ElevenLabs 음성 Provider에 관한 자세한 정보를 확인하세요.

**PlayAI**:

```typescript
// PlayAI Voice Configuration
const voice = new PlayAIVoice({
  speechModel: {
    name: 'playai-voice', // Example model name
    speaker: 'emma', // Example speaker name
    apiKey: process.env.PLAYAI_API_KEY,
    language: 'en-US', // Language code
    speed: 1.0, // Speech speed
  },
  // PlayAI may not have a separate listening model
})
```

방문[PlayAI Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/playai) 에서 PlayAI 음성 Provider에 관한 자세한 정보를 확인하세요.

**Google**:

```typescript
// Google Voice Configuration
const voice = new GoogleVoice({
  speechModel: {
    name: 'en-US-Studio-O', // Example model name
    apiKey: process.env.GOOGLE_API_KEY,
    languageCode: 'en-US', // Language code
    gender: 'FEMALE', // Voice gender
    speakingRate: 1.0, // Speaking rate
  },
  listeningModel: {
    name: 'en-US', // Example model name
    sampleRateHertz: 16000, // Sample rate
  },
})
```

방문[Google Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/google) 에서 Google 음성 Provider에 관한 자세한 정보를 확인하세요.

**Cloudflare**:

```typescript
// Cloudflare Voice Configuration
const voice = new CloudflareVoice({
  speechModel: {
    name: 'cloudflare-voice', // Example model name
    accountId: process.env.CLOUDFLARE_ACCOUNT_ID,
    apiToken: process.env.CLOUDFLARE_API_TOKEN,
    language: 'en-US', // Language code
    format: 'mp3', // Audio format
  },
  // Cloudflare may not have a separate listening model
})
```

방문[Cloudflare Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/cloudflare) 에서 Cloudflare 음성 Provider에 관한 자세한 정보를 확인하세요.

**Deepgram**:

```typescript
// Deepgram Voice Configuration
const voice = new DeepgramVoice({
  speechModel: {
    name: 'nova-2', // Example model name
    speaker: 'aura-english-us', // Example speaker name
    apiKey: process.env.DEEPGRAM_API_KEY,
    language: 'en-US', // Language code
    tone: 'formal', // Tone setting
  },
  listeningModel: {
    name: 'nova-2', // Example model name
    format: 'flac', // Audio format
  },
})
```

방문[Deepgram Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/deepgram) 에서 Deepgram 음성 Provider에 관한 자세한 정보를 확인하세요.

**Inworld**:

```typescript
// Inworld Voice Configuration
const voice = new InworldVoice({
  speechModel: {
    name: 'inworld-tts-2',
    apiKey: process.env.INWORLD_API_KEY,
  },
  listeningModel: {
    name: 'groq/whisper-large-v3',
    apiKey: process.env.INWORLD_API_KEY,
  },
  speaker: 'Dennis',
  audioEncoding: 'MP3',
  sampleRateHertz: 48000,
  language: 'en-US',
})

// Per-call options: `deliveryMode` is honored only by `inworld-tts-2`.
const audioStream = await voice.speak('Hello!', {
  deliveryMode: 'BALANCED', // 'STABLE' | 'BALANCED' | 'CREATIVE'
  language: 'en-US', // BCP-47 per-call override
})
```

방문[Inworld Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/inworld) 에서 Inworld 음성 Provider에 관한 자세한 정보를 확인하세요.

**Speechify**:

```typescript
// Speechify Voice Configuration
const voice = new SpeechifyVoice({
  speechModel: {
    name: 'speechify-voice', // Example model name
    speaker: 'matthew', // Example speaker name
    apiKey: process.env.SPEECHIFY_API_KEY,
    language: 'en-US', // Language code
    speed: 1.0, // Speech speed
  },
  // Speechify may not have a separate listening model
})
```

방문[Speechify Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/speechify) 에서 Speechify 음성 Provider에 관한 자세한 정보를 확인하세요.

**Sarvam**:

```typescript
// Sarvam Voice Configuration
const voice = new SarvamVoice({
  speechModel: {
    model: 'bulbul:v3', // TTS model (bulbul:v2 or bulbul:v3)
    apiKey: process.env.SARVAM_API_KEY,
    language: 'en-IN', // BCP-47 language code
  },
  listeningModel: {
    model: 'saarika:v2.5', // STT model (saarika:v2.5 or saaras:v3)
    apiKey: process.env.SARVAM_API_KEY,
  },
  speaker: 'shubh', // Default bulbul:v3 speaker
})
```

방문[Sarvam Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/sarvam) 에서 Sarvam 음성 Provider에 관한 자세한 정보를 확인하세요.

**Murf**:

```typescript
// Murf Voice Configuration
const voice = new MurfVoice({
  speechModel: {
    name: 'murf-voice', // Example model name
    apiKey: process.env.MURF_API_KEY,
    language: 'en-US', // Language code
    emotion: 'happy', // Emotion setting
  },
  // Murf may not have a separate listening model
})
```

방문[Murf Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/murf) 에서 Murf 음성 Provider에 관한 자세한 정보를 확인하세요.

**OpenAI Realtime**:

```typescript
// OpenAI Realtime Voice Configuration
const voice = new OpenAIRealtimeVoice({
  speechModel: {
    name: 'gpt-3.5-turbo', // Example model name
    apiKey: process.env.OPENAI_API_KEY,
    language: 'en-US', // Language code
  },
  listeningModel: {
    name: 'whisper-1', // Example model name
    apiKey: process.env.OPENAI_API_KEY,
    format: 'ogg', // Audio format
  },
  speaker: 'alloy', // Example speaker name
})
```

OpenAI Realtime 음성 제공자에 대한 자세한 내용은[OpenAI Realtime Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/openai-realtime).

**xAI Realtime**:

```typescript
// xAI Realtime Voice Configuration
const voice = new XAIRealtimeVoice({
  apiKey: process.env.XAI_API_KEY,
  model: 'grok-voice-think-fast-1.0',
  speaker: 'eve',
  instructions: 'You are a concise voice assistant.',
  turnDetection: {
    type: 'server_vad',
    threshold: 0.85,
    silence_duration_ms: 1000,
    prefix_padding_ms: 333,
  },
  audio: {
    input: { format: { type: 'audio/pcm', rate: 24000 } },
    output: { format: { type: 'audio/pcm', rate: 24000 } },
  },
  serverTools: [
    { type: 'web_search' },
    {
      type: 'mcp',
      server_url: 'https://mcp.example.com/mcp',
      server_label: 'business-tools',
    },
  ],
})
```

방문[xAI Realtime Voice Reference](https://mastra.zisheng.pro/ko/reference/voice/xai-realtime) 에서 xAI 실시간 음성 Provider에 관한 자세한 정보를 확인하세요.

**Google Gemini Live**:

```typescript
// Google Gemini Live Voice Configuration
const voice = new GeminiLiveVoice({
  speechModel: {
    name: 'gemini-2.0-flash-exp', // Example model name
    apiKey: process.env.GOOGLE_API_KEY,
  },
  speaker: 'Puck', // Example speaker name
  // Google Gemini Live is a realtime bidirectional API without separate speech and listening models
})
```

방문[Google Gemini Live Reference](https://mastra.zisheng.pro/ko/reference/voice/google-gemini-live) 에서 Google Gemini Live 음성 Provider에 관한 자세한 정보를 확인하세요.

**AWS Nova Sonic**:

```typescript
// AWS Nova Sonic Voice Configuration
const voice = new NovaSonicVoice({
  region: 'us-east-1',
  speaker: 'matthew',
  sessionConfig: {
    inferenceConfiguration: {
      temperature: 0.7,
      maxTokens: 1024,
    },
    turnDetectionConfiguration: {
      endpointingSensitivity: 'MEDIUM',
    },
  },
  // AWS Nova Sonic is a realtime bidirectional API without separate speech and listening models
})
```

방문[AWS Nova Sonic Reference](https://mastra.zisheng.pro/ko/reference/voice/aws-nova-sonic) 에서 AWS Nova Sonic 음성 Provider에 관한 자세한 정보를 확인하세요.

**Inworld Realtime**:

```typescript
// Inworld Realtime Voice Configuration
const voice = new InworldRealtimeVoice({
  apiKey: process.env.INWORLD_API_KEY,
  model: 'inworld/models/gemma-4-26b-a4b-it',
  speaker: 'Sarah',
  // Typed Inworld realtime knobs (semantic VAD, playback speed, MCP tool routing, ...)
  session: {
    audio: {
      output: { speed: 1.1 },
      input: { turn_detection: { type: 'semantic_vad', eagerness: 'high' } },
    },
  },
})
```

방문[Inworld Realtime Reference](https://mastra.zisheng.pro/ko/reference/voice/inworld-realtime) 에서 Inworld Realtime 음성 Provider에 관한 자세한 정보를 확인하세요.

**AI SDK**:

```typescript
// AI SDK Voice Configuration
import { CompositeVoice } from '@mastra/core/voice'
import { openai } from '@ai-sdk/openai'
import { elevenlabs } from '@ai-sdk/elevenlabs'

// Use AI SDK models directly - no need to install separate packages
const voice = new CompositeVoice({
  input: openai.transcription('whisper-1'), // AI SDK transcription
  output: elevenlabs.speech('eleven_turbo_v2'), // AI SDK speech
})

// Works seamlessly with your agent
const voiceAgent = new Agent({
  id: 'aisdk-voice-agent',
  name: 'AI SDK Voice Agent',
  instructions: 'You are a helpful assistant with voice capabilities.',
  model: 'openai/gpt-5.6-sol',
  voice,
})
```

### 여러 음성 Provider 사용

이 예에서는 Mastra에서 STT(음성-텍스트)용 OpenAI와 TTS(텍스트 음성 변환)용 PlayAI라는 두 가지 음성 공급자를 만들고 사용하는 방법을 보여줍니다.

필요한 구성을 사용하여 음성 공급자의 인스턴스를 만드는 것부터 시작하세요.

```typescript
import { OpenAIVoice } from '@mastra/voice-openai'
import { PlayAIVoice } from '@mastra/voice-playai'
import { CompositeVoice } from '@mastra/core/voice'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'

// Initialize OpenAI voice for STT
const input = new OpenAIVoice({
  listeningModel: {
    name: 'whisper-1',
    apiKey: process.env.OPENAI_API_KEY,
  },
})

// Initialize PlayAI voice for TTS
const output = new PlayAIVoice({
  speechModel: {
    name: 'playai-voice',
    apiKey: process.env.PLAYAI_API_KEY,
  },
})

// Combine the providers using CompositeVoice
const voice = new CompositeVoice({
  input,
  output,
})

// Implement voice interactions using the combined voice provider
const audioStream = getMicrophoneStream() // Assume this function gets audio input
const transcript = await voice.listen(audioStream)

// Log the transcribed text
console.log('Transcribed text:', transcript)

// Convert text to speech
const responseAudio = await voice.speak(`You said: ${transcript}`, {
  speaker: 'default', // Optional: specify a speaker,
  responseFormat: 'wav', // Optional: specify a response format
})

// Play the audio response
playAudio(responseAudio)
```

### AI SDK Model 공급자 사용

AI SDK Model을 직접 사용할 수도 있습니다.`CompositeVoice`:

```typescript
import { CompositeVoice } from '@mastra/core/voice'
import { openai } from '@ai-sdk/openai'
import { elevenlabs } from '@ai-sdk/elevenlabs'
import { playAudio, getMicrophoneStream } from '@mastra/node-audio'

// Use AI SDK models directly - no provider setup needed
const voice = new CompositeVoice({
  input: openai.transcription('whisper-1'), // AI SDK transcription
  output: elevenlabs.speech('eleven_turbo_v2'), // AI SDK speech
})

// Works the same way as Mastra providers
const audioStream = getMicrophoneStream()
const transcript = await voice.listen(audioStream)

console.log('Transcribed text:', transcript)

// Convert text to speech
const responseAudio = await voice.speak(`You said: ${transcript}`, {
  speaker: 'Rachel', // ElevenLabs voice
})

playAudio(responseAudio)
```

AI SDK Model을 Mastra 공급자와 혼합할 수도 있습니다.

```typescript
import { CompositeVoice } from '@mastra/core/voice'
import { PlayAIVoice } from '@mastra/voice-playai'
import { groq } from '@ai-sdk/groq'

const voice = new CompositeVoice({
  input: groq.transcription('whisper-large-v3'), // AI SDK for STT
  output: new PlayAIVoice(), // Mastra provider for TTS
})
```

CompositeVoice에 대한 자세한 내용은[CompositeVoice Reference](https://mastra.zisheng.pro/ko/reference/voice/composite-voice).

## 더 많은 리소스

- [합성음성](https://mastra.zisheng.pro/ko/reference/voice/composite-voice)
- [마스트라보이스](https://mastra.zisheng.pro/ko/reference/voice/mastra-voice)
- [오픈AI 보이스](https://mastra.zisheng.pro/ko/reference/voice/openai)
- [OpenAI 실시간 음성](https://mastra.zisheng.pro/ko/reference/voice/openai-realtime)
- [xAI 실시간 음성](https://mastra.zisheng.pro/ko/reference/voice/xai-realtime)
- [Azure 보이스](https://mastra.zisheng.pro/ko/reference/voice/azure)
- [구글 보이스](https://mastra.zisheng.pro/ko/reference/voice/google)
- [Google Gemini 라이브 보이스](https://mastra.zisheng.pro/ko/reference/voice/google-gemini-live)
- [AWS Nova Sonic 음성](https://mastra.zisheng.pro/ko/reference/voice/aws-nova-sonic)
- [딥그램 보이스](https://mastra.zisheng.pro/ko/reference/voice/deepgram)
- [인월드 보이스](https://mastra.zisheng.pro/ko/reference/voice/inworld)
- [라이브킷](https://mastra.zisheng.pro/ko/reference/voice/livekit)
- [플레이AI 보이스](https://mastra.zisheng.pro/ko/reference/voice/playai)
- [음성 예](https://github.com/mastra-ai/voice-examples)